© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257560
    Prev
    Next
    INDEX
    Explanations

    language switching confirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     v
    0.23
     P
    0.22
     Bon
    0.22
     V
    0.22
     ID
    0.22
     locations
    0.22
     B
    0.22
     bon
    0.22
     blockchain
    0.21
     CSV
    0.21
    POSITIVE LOGITS
    Actually
    0.21
    öyle
    0.20
    étais
    0.20
    বোধ
    0.19
     Actually
    0.19
    頖
    0.19
     Поэтому
    0.19
    তারা
    0.19
    сима
    0.19
    婷
    0.18
    Activations Density 0.011%

    No Known Activations